mlsanityData to 14 Oct 2026

HEAT: Hyperedge Attention Networks

arXiv 2201.12113 ↗First posted 28 Jan 2022cs.LG cs.SEcited by 13

Not on the map. Why?

Abstract (arXiv)

Learning from structured data is a core machine learning task. Commonly, such data is represented as graphs, which normally only consider (typed) binary relationships between pairs of nodes. This is a substantial limitation for many domains with highly-structured data. One important such domain is source code, where hypergraph-based representations can better capture the semantically rich and structured nature of code. In this work, we present HEAT, a neural model capable of representing typed and qualified hypergraphs, where each hyperedge explicitly qualifies how participating nodes contribute. It can be viewed as a generalization of both message passing neural networks and Transformers. We evaluate HEAT on knowledge base completion and on bug detection and repair using a novel hypergraph representation of programs. In both settings, it outperforms strong baselines, indicating its power and generality.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 30 of its 43 references that are in the map. First posted on arXiv 28 Jan 2022.

Builds on

30 of 43 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2017Graph Attention Networkscited by 8,923
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  6. 2016Layer Normalizationcited by 5,669
  7. 2021Program Synthesis with Large Language Modelscited by 3,637
  8. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  9. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  10. 2017Deep Setscited by 1,421
  11. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  12. 2015Gated Graph Sequence Neural Networkscited by 796
18 more
  1. 2017Convolutional 2D Knowledge Graph Embeddingscited by 730
  2. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  3. 2018Hypergraph Neural Networkscited by 488
  4. 2017DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoningcited by 266
  5. 2019Hypergraph Convolution and Hypergraph Attentioncited by 228
  6. 2017A Survey of Machine Learning for Big Code and Naturalnesscited by 221
  7. 2017Learning to Represent Programs with Graphscited by 220
  8. 2017End-to-End Differentiable Provingcited by 161
  9. 2021UniGNN: a Unified Framework for Graph and Hypergraph Neural Networkscited by 130
  10. 2021You are AllSet: A Multiset Function Framework for Hypergraph Neural Networkscited by 127
  11. 2020Message Passing for Hyper-Relational Knowledge Graphscited by 79
  12. 2019Hyper-SAGNN: a self-attention based graph neural network for hypergraphscited by 69
  13. 2021Self-Supervised Bug Detection and Repaircited by 59
  14. 2016On the representation and embedding of knowledge bases beyond binary relationscited by 55
  15. 2018Structured Neural Summarizationcited by 54
  16. 2020HyperSAGE: Generalizing Inductive Representation Learning on Hypergraphscited by 54
  17. 2016ProjE: Embedding Projection for Knowledge Graph Completioncited by 26
  18. 2021Improving Hyper-Relational Knowledge Graph Completioncited by 18

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 5; 2024: 5.

13 papers.

Sort:

  1. 2024Position: Topological Deep Learning is the New Frontier for Relational Learningcited by 66
  2. 2022Message passing all the way upcited by 47
  3. 2023Sheaf Hypergraph Networkscited by 34
  4. 2023Large Language Models of Code Fail at Completing Code with Potential Bugscited by 29
  5. 2023From Hypergraph Energy Functions to Hypergraph Neural Networkscited by 18
  6. 2022A Hypergraph Neural Network Framework for Learning Hyperedge-Dependent Node Embeddingscited by 9
  7. 2024Link Prediction with Relational Hypergraphscited by 9
  8. 2022A Library for Representing Python Programs as Graphs for Machine Learningcited by 4
  9. 2023UniG-Encoder: A Universal Feature Encoder for Graph and Hypergraph Node Classificationcited by 4
  10. 2024SPHINX: Structural Prediction using Hypergraph Inference Networkcited by 3
  11. 2023Hypergraph Node Representation Learning with One-Stage Message Passingcited by 2
  12. 2024Inference of Sequential Patterns for Neural Message Passing in Temporal Graphscited by 1
1 more
  1. 2024Explaining Hypergraph Neural Networks: From Local Explanations to Global Conceptscited by 1